© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 30964
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly in a context of news or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.13
    0.7%
    177
    +0.13
    0.7%
    322
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    370
    +0.13
    0.02
    71
    +0.13
    0.01
    251
    +0.13
    0.01
    Negative Logits
    ĥ½
    -2.52
    ĨĴ
    -2.16
    ĻĤ
    -2.10
    ¥
    -2.08
    ĵ
    -2.03
    Ī
    -1.91
    Ń
    -1.88
    »¿
    -1.82
    Ĺ
    -1.81
    Ĥ
    -1.79
    POSITIVE LOGITS
    Set
    1.44
    pson
    1.42
     quo
    1.40
    stown
    1.40
    Dispatch
    1.39
    piece
    1.38
    witz
    1.37
    press
    1.36
     recognizes
    1.35
     aligned
    1.34
    Activations Density 0.036%

    No Known Activations